{"id":18257335,"url":"https://github.com/socxin/eai80","last_synced_at":"2025-06-22T17:40:22.483Z","repository":{"id":52685350,"uuid":"204860378","full_name":"SoCXin/EAI80","owner":"SoCXin","description":"L6: Gree Edgeless Cortex M4F SoC (EAI80)","archived":false,"fork":false,"pushed_at":"2022-12-26T20:40:29.000Z","size":44575,"stargazers_count":2,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-04T08:57:46.229Z","etag":null,"topics":["cnn","cortex-m4","dual-core","kpu","qitas","soc"],"latest_commit_sha":null,"homepage":"","language":"C","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SoCXin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-08-28T06:08:52.000Z","updated_at":"2022-07-25T08:45:45.000Z","dependencies_parsed_at":"2023-01-31T01:31:05.651Z","dependency_job_id":null,"html_url":"https://github.com/SoCXin/EAI80","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SoCXin/EAI80","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SoCXin%2FEAI80","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SoCXin%2FEAI80/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SoCXin%2FEAI80/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SoCXin%2FEAI80/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SoCXin","download_url":"https://codeload.github.com/SoCXin/EAI80/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SoCXin%2FEAI80/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261337156,"owners_count":23143842,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cnn","cortex-m4","dual-core","kpu","qitas","soc"],"created_at":"2024-11-05T10:25:41.598Z","updated_at":"2025-06-22T17:40:17.469Z","avatar_url":"https://github.com/SoCXin.png","language":"C","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [EAI80](https://github.com/SoCXin/EAI80)\n\n[![sites](http://182.61.61.133/link/resources/SoC.png)](http://www.SoC.Xin)\n\n#### [Vendor](https://github.com/SoCXin/Vendor)：[Gree Edgeless](https://github.com/SoCXin/Gree)\n#### [Core](https://github.com/SoCXin/Cortex)：[Cortex M4](https://github.com/SoCXin/CM4)\n#### [Level](https://github.com/SoCXin/Level)：2 x 200MHz x 1.25DMIPS/MHz (500DMIPS) , CNN-NPU @ 300MHz 300GOPS\n\n## [简介](https://github.com/SoCXin/EAI80/wiki)\n\n[EAI80](https://github.com/SoCXin/EAI80)是一个多核微控制器，实现了双核Cortex-M4核。所有核心都可以访问完整的内存映射。ARM Cortex-M4用作主处理器。另一个ARM Cortex-M4内核可以作为协处理器来协助ARM Cortex-M4并执行复杂的数学计算。\n\n支持主流CNN模式，如Resnet-18, Resnet-34, Vgg16, GoogleNet, Lenet等，卷积与内核大小从1到7，频道/特征数高达512，最大/平均池功能与内核。\n\n* CPU Dual-Cortex M4F@200MHz 500DMIPS\n* AI-NPU：CNN-NPU @300 MHz 300GOPS,144MAC/cycle, EER up to 1TOPS/W, for image recognition scenario.\n* 2D Graph :Dual-Camera Max\n* Up to 384KB of SRAM, 256KB for CNN-NPU (Share with CPU) ,Up to 8MB of SIP-SDRAM\n\n* 3x I2C interfaces\n* 8x UARTs with full-duplex data exchange,\n* 2x SPIs, full-duplex synchronous and single-wire bidirectional mode and 4- to 16-bit word frames\n* 1x CAN 2.0B interfaces\n* 1x USB 2.0 full-speed device/host/OTG controller with off-chip PHY\n\n#### 关键特性\n\n* CNN-NPU @300 MHz 300GOPS\n* Dual Cortex M4F@200MHz 500DMIPS\n\n\n### [收录资源](https://github.com/SoCXin/EAI80)\n\n* [文档](docs/)\n* [资源](src/)\n\n### [选型建议](https://github.com/SoCXin)\n\n[EAI80](https://github.com/SoCXin/EAI80)是一款新的边缘计算体系MCU，集成NPU，可应用于语音控制，计算机视觉-物体和生物(脸，身体，姿势)的检测和识别，vSLAM，边缘计算等。\n\n后续缺乏相应支持，生态不够完善，个人开发较难。\n###  [www.SoC.xin(芯)](http://www.SoC.Xin)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsocxin%2Feai80","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsocxin%2Feai80","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsocxin%2Feai80/lists"}